yt_dlp/extractor/tv2hu.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     UnsupportedError,
   4     traverse_obj,
   5 )
   6
   7
   8 class TV2HuIE(InfoExtractor):
   9     IE_NAME = 'tv2play.hu'
  10     _VALID_URL = r'https?://(?:www\.)?tv2play\.hu/(?!szalag/)(?P<id>[^#&?]+)'
  11     _TESTS = [{
  12         'url': 'https://tv2play.hu/mintaapak/mintaapak_213_epizod_resz',
  13         'info_dict': {
  14             'id': '249240',
  15             'ext': 'mp4',
  16             'title': 'Mintaapák - 213. epizód',
  17             'series': 'Mintaapák',
  18             'duration': 2164,
  19             'description': 'md5:7350147e75485a59598e806c47967b07',
  20             'thumbnail': r're:^https?://.*\.jpg$',
  21             'release_date': '20210825',
  22             'episode_number': 213,
  23         },
  24         'params': {
  25             'skip_download': True,
  26         },
  27     }, {
  28         'url': 'https://tv2play.hu/taxi_2',
  29         'md5': '585e58e2e090f34603804bb2c48e98d8',
  30         'info_dict': {
  31             'id': '199363',
  32             'ext': 'mp4',
  33             'title': 'Taxi 2',
  34             'series': 'Taxi 2',
  35             'duration': 5087,
  36             'description': 'md5:47762155dc9a50241797ded101b1b08c',
  37             'thumbnail': r're:^https?://.*\.jpg$',
  38             'release_date': '20210118',
  39         },
  40         'params': {
  41             'skip_download': True,
  42         },
  43     }]
  44
  45     def _real_extract(self, url):
  46         video_id = self._match_id(url)
  47         json_data = self._download_json(f'https://tv2play.hu/api/search/{video_id}', video_id)
  48
  49         if json_data['contentType'] == 'showpage':
  50             ribbon_ids = traverse_obj(json_data, ('pages', ..., 'tabs', ..., 'ribbonIds'), get_all=False, expected_type=list)
  51             entries = [self.url_result(f'https://tv2play.hu/szalag/{ribbon_id}',
  52                                        ie=TV2HuSeriesIE.ie_key(), video_id=ribbon_id) for ribbon_id in ribbon_ids]
  53             return self.playlist_result(entries, playlist_id=video_id)
  54         elif json_data['contentType'] != 'video':
  55             raise UnsupportedError(url)
  56
  57         video_id = str(json_data['id'])
  58         player_id = json_data.get('playerId')
  59         series_json = json_data.get('seriesInfo', {})
  60
  61         video_json_url = self._download_json(f'https://tv2play.hu/api/streaming-url?playerId={player_id}', video_id)['url']
  62         video_json = self._download_json(video_json_url, video_id)
  63         m3u8_url = self._proto_relative_url(traverse_obj(video_json, ('bitrates', 'hls')))
  64         formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id)
  65
  66         return {
  67             'id': video_id,
  68             'title': json_data['title'],
  69             'series': json_data.get('seriesTitle'),
  70             'duration': json_data.get('length'),
  71             'description': json_data.get('description'),
  72             'thumbnail': 'https://tv2play.hu' + json_data.get('thumbnailUrl'),
  73             'release_date': json_data.get('uploadedAt').replace('.', ''),
  74             'season_number': series_json.get('seasonNr'),
  75             'episode_number': series_json.get('episodeNr'),
  76             'formats': formats,
  77             'subtitles': subtitles,
  78         }
  79
  80
  81 class TV2HuSeriesIE(InfoExtractor):
  82     IE_NAME = 'tv2playseries.hu'
  83     _VALID_URL = r'https?://(?:www\.)?tv2play\.hu/szalag/(?P<id>[^#&?]+)'
  84
  85     _TESTS = [{
  86         'url': 'https://tv2play.hu/szalag/59?rendezes=nepszeruseg',
  87         'playlist_mincount': 284,
  88         'info_dict': {
  89             'id': '59',
  90         },
  91     }]
  92
  93     def _real_extract(self, url):
  94         playlist_id = self._match_id(url)
  95         json_data = self._download_json(f'https://tv2play.hu/api/ribbons/{playlist_id}/0?size=100000', playlist_id)
  96         entries = []
  97         for card in json_data.get('cards', []):
  98             video_id = card.get('slug')
  99             if video_id:
 100                 entries.append(self.url_result(
 101                     f'https://tv2play.hu/{video_id}', TV2HuIE, video_id))
 102
 103         return self.playlist_result(entries, playlist_id=playlist_id)